© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 28565
    Prev
    Next
    INDEX
    Explanations

    quotes or dialogue within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    478
    +0.14
    0.8%
    111
    +0.12
    0.7%
    369
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    250
    +0.14
    0.03
    505
    +0.12
    0.02
    228
    +0.10
    0.02
    Negative Logits
    pike
    -1.64
     trough
    -1.56
    alities
    -1.56
    >/
    -1.55
    ality
    -1.55
    wards
    -1.53
    ward
    -1.53
    ctors
    -1.46
     now
    -1.43
    kins
    -1.40
    POSITIVE LOGITS
    Į
    4.41
    Ĭ
    4.32
    ®
    4.25
    ĥ
    4.13
    ¿
    3.97
    ·¸
    3.93
    ¡
    3.88
    ↵
    3.88
    ↵
    3.88
     ↵
    3.88
    Activations Density 0.150%

    No Known Activations